© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42749
    Prev
    Next
    INDEX
    Explanations

    wearable or insertable personal items

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on technical product or device names (e.g. “contact lens,” “tampon,” “earpiece”), i.e. concrete manufactured objects.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conosciuto
    -1.38
     голос
    -1.15
     then
    -1.11
     meglio
    -1.10
     if
    -1.10
    場合
    -1.09
     случае
    -1.09
     dichiarato
    -1.08
     Lettres
    -1.08
     wymaga
    -1.08
    POSITIVE LOGITS
     your
    1.44
     each
    1.43
    each
    1.34
    🪟
    1.28
     \&
    1.25
    ญี่ป
    1.25
     komfort
    1.22
     spend
    1.15
    ască
    1.15
    Each
    1.14
    Activations Density 0.042%

    No Known Activations